ResearchTasksMulti-step ReasoningMulti-step ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedBabyAI-Text UnlockLocal (No Change)AEC95Success Rate2Jun 29, 2026PreviousPage 2 of 2Next